Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs

• URL: http://arxiv.org/abs/2504.13429v1
• Date: Fri, 18 Apr 2025 03:01:00 GMT
• Title: Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs
• Authors: Shenzhi Yang, Bin Liang, An Liu, Lin Gui, Xingkai Yao, Xiaofang Zhang,
• Abstract summary: We propose NODESAFE: reducing the generation of extreme scores of nodes by adding two optimization terms that make the negative energy scores bounded and mitigate the logit shift.<n> Experimental results show that our approach dramatically improves the ability of GNNs to detect OOD data at the node level.
• Score: 13.357430716033337
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Given the critical role of graphs in real-world applications and their high-security requirements, improving the ability of graph neural networks (GNNs) to detect out-of-distribution (OOD) data is an urgent research problem. The recent work GNNSAFE proposes a framework based on the aggregation of negative energy scores that significantly improves the performance of GNNs to detect node-level OOD data. However, our study finds that score aggregation among nodes is susceptible to extreme values due to the unboundedness of the negative energy scores and logit shifts, which severely limits the accuracy of GNNs in detecting node-level OOD data. In this paper, we propose NODESAFE: reducing the generation of extreme scores of nodes by adding two optimization terms that make the negative energy scores bounded and mitigate the logit shift. Experimental results show that our approach dramatically improves the ability of GNNs to detect OOD data at the node level, e.g., in detecting OOD data induced by Structure Manipulation, the metric of FPR95 (lower is better) in scenarios without (with) OOD data exposure are reduced from the current SOTA by 28.4% (22.7%).

Related papers

• Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphs [61.226857589092]
  OOD detection on nodes in graph learning remains underexplored.<n>GNNSafe adapted energy-based detection to the graph domain with state-of-the-art performance.<n>We introduce DeGEM, which decomposes the learning process into two parts: a graph encoder that leverages topology information for node representations and an energy head that operates in latent space.
  arXiv  Detail & Related papers  (2025-02-25T07:20:00Z)
• GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation [26.062189631691545]
  Out-of-distribution (OOD) test instances still pose a great challenge for graph neural networks (GNNs) We propose the GOLD framework for graph OOD detection, an implicit adversarial learning pipeline with synthetic OOD exposure without pre-trained models.
  arXiv  Detail & Related papers  (2025-02-09T05:19:53Z)
• HGOE: Hybrid External and Internal Graph Outlier Exposure for Graph Out-of-Distribution Detection [78.47008997035158]
  Graph data exhibits greater diversity but lower robustness to perturbations, complicating the integration of outliers. We propose the introduction of textbfHybrid External and Internal textbfGraph textbfOutlier textbfExposure (HGOE) to improve graph OOD detection performance.
  arXiv  Detail & Related papers  (2024-07-31T16:55:18Z)
• Online GNN Evaluation Under Test-time Graph Distribution Shifts [92.4376834462224]
  A new research problem, online GNN evaluation, aims to provide valuable insights into the well-trained GNNs's ability to generalize to real-world unlabeled graphs. We develop an effective learning behavior discrepancy score, dubbed LeBeD, to estimate the test-time generalization errors of well-trained GNN models.
  arXiv  Detail & Related papers  (2024-03-15T01:28:08Z)
• Graph Out-of-Distribution Generalization via Causal Intervention [69.70137479660113]
  We introduce a conceptually simple yet principled approach for training robust graph neural networks (GNNs) under node-level distribution shifts. Our method resorts to a new learning objective derived from causal inference that coordinates an environment estimator and a mixture-of-expert GNN predictor. Our model can effectively enhance generalization with various types of distribution shifts and yield up to 27.4% accuracy improvement over state-of-the-arts on graph OOD generalization benchmarks.
  arXiv  Detail & Related papers  (2024-02-18T07:49:22Z)
• Energy-based Out-of-Distribution Detection for Graph Neural Networks [76.0242218180483]
  We propose a simple, powerful and efficient OOD detection model for GNN-based learning on graphs, which we call GNNSafe. GNNSafe achieves up to $17.0%$ AUROC improvement over state-of-the-arts and it could serve as simple yet strong baselines in such an under-developed area.
  arXiv  Detail & Related papers  (2023-02-06T16:38:43Z)
• Resisting Graph Adversarial Attack via Cooperative Homophilous Augmentation [60.50994154879244]
  Recent studies show that Graph Neural Networks are vulnerable and easily fooled by small perturbations. In this work, we focus on the emerging but critical attack, namely, Graph Injection Attack. We propose a general defense framework CHAGNN against GIA through cooperative homophilous augmentation of graph data and model.
  arXiv  Detail & Related papers  (2022-11-15T11:44:31Z)
• GANI: Global Attacks on Graph Neural Networks via Imperceptible Node Injections [20.18085461668842]
  Graph neural networks (GNNs) have found successful applications in various graph-related tasks. Recent studies have shown that many GNNs are vulnerable to adversarial attacks. In this paper, we focus on a realistic attack operation via injecting fake nodes.
  arXiv  Detail & Related papers  (2022-10-23T02:12:26Z)
• Uncertainty Aware Semi-Supervised Learning on Graph Data [18.695343563823798]
  We propose a multi-source uncertainty framework using a graph neural network (GNN) for node classification predictions. By collecting evidence from the labels of training nodes, the Graph-based Kernel Dirichlet distribution Estimation (GKDE) method is designed for accurately predicting node-level Dirichlet distributions. We found that dissonance-based detection yielded the best results on misclassification detection while vacuity-based detection was the best for OOD detection.
  arXiv  Detail & Related papers  (2020-10-24T04:56:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.